Evolutionary Optimization of Multimodal Functions Using Radial Basis Function Networks
Result description
This paper is aimed at optimization of black-box functions. We assume that these functions are time demanding and therefore our goal is to minimize the number of evalua- tions of these functions. As one of the today's most promising algorithms, the radial basis function network (RBFN) is presented. The novelty in our approach is the use of an evolutionary algorithm GRADE. Also several scenarios of creating new points in the process of the approximation are presented. In comparison with the original approach, the number of needed evaluations of a test function is reduced approximately by a factor of two. To show the ability of the proposed methodology, the suite of twenty multi-modal functions is used along with one real-world problem of optimal controlof structures undergoing large displacements.
Keywords
approximationevolutionary algorithmsgenetic algorithmsglobal optimizationmulti-modal problemsradial basis function network
The result's identifiers
Result code in IS VaVaI
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Evolutionary Optimization of Multimodal Functions Using Radial Basis Function Networks
Original language description
This paper is aimed at optimization of black-box functions. We assume that these functions are time demanding and therefore our goal is to minimize the number of evalua- tions of these functions. As one of the today's most promising algorithms, the radial basis function network (RBFN) is presented. The novelty in our approach is the use of an evolutionary algorithm GRADE. Also several scenarios of creating new points in the process of the approximation are presented. In comparison with the original approach, the number of needed evaluations of a test function is reduced approximately by a factor of two. To show the ability of the proposed methodology, the suite of twenty multi-modal functions is used along with one real-world problem of optimal controlof structures undergoing large displacements.
Czech name
Evoluční optimalizace vícemodálních funkcí s využitím sítí s radiální bází
Czech description
Cílem článku je optimalizace tzv. black-box funkcí. Cílem bylo prozkoumat požití sítí s radiální bází (RBFN), které se jeví jako slibný algoritmus. Novinkou je využití vlastního evolučního algoritmu GRADE k nalezení optima RBFN aproximace. V porovnání soriginální prací se podařilo snížít počet potřebných evaluací na polovinu. Praktické využití je ukázáno na sadě dvaceni matematických optimalizačních problémů a jedné reálné úloze z oblasti řízení konstrukcí za velkých deformací.
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
GA103/06/1856: Nanoindentation Tests for the Evaluation of Cement Paste Physical Properties
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2008
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2008 AIAA Meeting Papers on Disc, Vol. 13, No. 12 (MAO)
ISBN
978-1-56347-947-2
ISSN
—
e-ISSN
—
Number of pages
13
Pages from-to
—
Publisher name
American Institute of Aeronautics and Astronautics
Place of publication
Reston
Event location
Victoria
Event date
Sep 10, 2008
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—
Basic information
Result type
D - Article in proceedings
CEP
JD - Use of computers, robotics and its application
Year of implementation
2008